Adversarial Robustness of Flow-based Image Super-Resolution

Junha Park, Jun-Ho Choi, Jong-Seok Lee

Abstract: This paper investigates the robustness of deep image super-resolution models using normalizing flow against adversarial attacks. Attack methods specific to flow-based super-resolution models are formulated, and the performance and influences of the attacks are analyzed. We show that flow-based super-resolution models are highly vulnerable to attacks, which are even more serious than other super-resolution models. Potential remedies to the vulnerability are also evaluated.